Triple
T32974429
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Problem of Thor Bridge |
E843614
|
entity |
| Predicate | suspectedCharacter |
P21177
|
FINISHED |
| Object | Grace Dunbar |
—
|
NE NERFINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Grace Dunbar | Statement: [The Problem of Thor Bridge, suspectedCharacter, Grace Dunbar]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: suspectedCharacter Context triple: [The Problem of Thor Bridge, suspectedCharacter, Grace Dunbar]
-
A.
questionedCharacter
Indicates that one entity directed questions or an interrogation toward another entity.
-
B.
suspectedPerpetrator
chosen
Indicates that an entity is believed or alleged to be the person responsible for committing a particular harmful or illegal act.
-
C.
possibleSourceCharacter
Indicates that an entity is a candidate or potential originator of a given character (e.g., a symbol, glyph, or textual character) in a mapping or derivation relationship.
-
D.
unseenCharacter
Indicates that a character exists in the narrative or context but does not appear directly or visibly in the current scene or depiction.
-
E.
accusedCharacterPortrayedBy
Indicates that a particular actor or performer plays the role of the character who is accused within a given work.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69f3494b9fc48190bb61c955ba471275 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69f6db6af1d88190989810182354d60f |
completed | May 3, 2026, 5:21 a.m. |
| PD | Predicate disambiguation | batch_69f6d82d068c8190940a3200ed760e38 |
completed | May 3, 2026, 5:07 a.m. |
Created at: May 1, 2026, 1:22 a.m.